---
license: apache-2.0
base_model: nandovallec/whisper-tiny-bg-l
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-order
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# whisper-tiny-order

This model is a fine-tuned version of [nandovallec/whisper-tiny-bg-l](https://huggingface.co/nandovallec/whisper-tiny-bg-l) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0022
- Wer: 0.0

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 64
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| 0.0186        | 4.0   | 5    | 0.0621          | 5.0 |
| 0.008         | 8.0   | 10   | 0.0235          | 0.0 |
| 0.0018        | 12.0  | 15   | 0.0049          | 0.0 |
| 0.001         | 16.0  | 20   | 0.0030          | 0.0 |
| 0.0005        | 20.0  | 25   | 0.0024          | 0.0 |
| 0.0007        | 24.0  | 30   | 0.0022          | 0.0 |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0